AS-ASR: A Lightweight Framework for Aphasia-Specific Automatic Speech Recognition

IEEE Biomedical Circuits and Systems Conference (BioCAS), pp. 76–80

Abstract

This paper proposes AS-ASR, a lightweight aphasiaspecific speech recognition framework based on Whisper-tiny, tailored for low-resource deployment on edge devices. Our approach introduces a hybrid training strategy that systematically combines standard and aphasic speech at varying ratios, enabling robust generalization, and a GPT-4-based reference enhancement method that refines noisy aphasic transcripts, improving supervision quality. We conduct extensive experiments across multiple data mixing configurations and evaluation settings. Results show that our fine-tuned model significantly outperforms the zero-shot baseline, reducing WER on aphasic speech by over $30 \%$ while preserving performance on standard speech. The proposed framework offers a scalable, efficient solution for realworld disordered speech recognition.

Authors 2

1. Chuanbing Huo

   Sanford Health

   Affiliation as printed

   Sanford Health,Minnesota,United States

2. Qinyu Chen Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden Institute of Advanced Computer Science (LIACS), Leiden University,The Netherlands